We propose an automatic feature generation by deep convolutional autoencoder (deep CAE) without lesion data. The main idea of the proposed method is based on anomaly detection. Deep CAE is trained by only normal volume patches. Trained deep CAE calculates low-dimensional features and reproduction error from 2.5 dimensional (2.5D) volume patch. The proposed method was evaluated experimentally with 150 chest CT cases. By using both previous features and the deep CAE based features, an improved classification performance was obtained; AUC=0.989 and ANODE=0.339.